|
--- |
|
license: apache-2.0 |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: distilgpt2-2k_clean_medical_articles_causal_language_model |
|
results: [] |
|
language: |
|
- en |
|
metrics: |
|
- perplexity |
|
--- |
|
|
|
# distilgpt2-2k_clean_medical_articles_causal_language_model |
|
|
|
This model is a fine-tuned version of [distilgpt2](https://huggingface.co/distilgpt2). |
|
It achieves the following results on the evaluation set: |
|
- Loss: 2.9268 |
|
|
|
## Model description |
|
|
|
This is a causal language modeling project. |
|
|
|
For more information on how it was created, check out the following link: https://github.com/DunnBC22/NLP_Projects/blob/main/Causal%20Language%20Modeling/2000%20Clean%20Medical%20Articles/2%2C000%20Clean%20Medical%20Articles%20-%20CLM.ipynb |
|
|
|
## Intended uses & limitations |
|
|
|
This model is intended to demonstrate my ability to solve a complex problem using technology. |
|
|
|
## Training and evaluation data |
|
|
|
Dataset Source: https://www.kaggle.com/datasets/trikialaaa/2k-clean-medical-articles-medicalnewstoday |
|
|
|
## Training procedure |
|
|
|
### Training hyperparameters |
|
|
|
The following hyperparameters were used during training: |
|
- learning_rate: 2e-05 |
|
- train_batch_size: 8 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 3 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 3.1211 | 1.0 | 1991 | 2.9740 | |
|
| 2.998 | 2.0 | 3982 | 2.9367 | |
|
| 2.9484 | 3.0 | 5973 | 2.9268 | |
|
|
|
Perplexity: 18.67 |
|
|
|
### Framework versions |
|
|
|
- Transformers 4.26.1 |
|
- Pytorch 1.12.1 |
|
- Datasets 2.9.0 |
|
- Tokenizers 0.12.1 |
